<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of distilbert-base-uncased on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.2274
- Accuracy: 0.9335
- F1: 0.9335
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
0.1747 | 1.0 | 250 | 0.1884 | 0.9295 | 0.9286 |
0.1219 | 2.0 | 500 | 0.1533 | 0.9345 | 0.9347 |
0.1014 | 3.0 | 750 | 0.1600 | 0.932 | 0.9324 |
0.081 | 4.0 | 1000 | 0.1592 | 0.9365 | 0.9367 |
0.065 | 5.0 | 1250 | 0.1787 | 0.935 | 0.9347 |
0.0511 | 6.0 | 1500 | 0.1874 | 0.934 | 0.9339 |
0.0419 | 7.0 | 1750 | 0.2131 | 0.935 | 0.9353 |
0.0351 | 8.0 | 2000 | 0.2151 | 0.934 | 0.9344 |
0.0292 | 9.0 | 2250 | 0.2269 | 0.933 | 0.9332 |
0.024 | 10.0 | 2500 | 0.2274 | 0.9335 | 0.9335 |
Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2